[PATCH v3] scsi: aic79xx: Fix NULL pointer dereference in device reset

[Andrew Luebke]

Since commit c67e63800446 ("scsi: aic79xx: Do not reference SCSI command
when resetting device") the device reset SCB has no SCSI command, but
ahd_linux_dev_reset() still sets its residual, and ahd_abort_scbs(),
which completes it, sets its status. Seen on an AIC-7902 when a failing
disk triggered a device reset, which killed the SCSI error handler:

  BUG: kernel NULL pointer dereference, address: 0000009c
  EIP: ahd_linux_dev_reset.cold+0xee/0x26e

Add NULL command checks to the accessors in aic79xx_osm.h. Also skip
autosense for an SCB without a command and complete it with ahd_done()
right away: the REQUEST SENSE path can clear SCB_DEVICE_RESET, after
which ahd_done() would dereference the missing command.

Fixes: c67e63800446 ("scsi: aic79xx: Do not reference SCSI command when resetting device")
Cc: stable@xxxxxxxxxxxxxxx
Reviewed-by: Hannes Reinecke <hare@xxxxxxxxxx>
Signed-off-by: Andrew Luebke <andrew.luebke@xxxxxxxxx>
Assisted-by: LLM
---

Notes:
    v3:
     - Complete an SCB that ahd_perform_autosense() declines with ahd_done().
       v2 left it on the pending list until a bus reset, which does not come
       with SG_SCSI_RESET_NO_ESCALATE (Sashiko AI review of v2). Such a reset
       now returns SUCCESS, as one answered with any other status does; in v2
       it timed out and returned FAILED. This is the only code change, so I
       kept Hannes's Reviewed-by.
     - Much shorter commit message (Hannes). Sorry for the overlong
       descriptions in v1 and v2.
    v2: https://patchwork.kernel.org/project/linux-scsi/patch/20261023170330.269844-1-andrew.luebke@xxxxxxxxx/
     - Put the NULL checks into the ahd_cmd_*() helpers where one exists, and
       keep the now safe ahd_set_residual() call in ahd_linux_dev_reset()
       (Hannes).
     - Skip autosense for an SCB without a command (Sashiko AI review of v1).
    v1: https://patchwork.kernel.org/project/linux-scsi/patch/20261020221530.2606178-1-andrew.luebke@xxxxxxxxx/
    
    Tested on an AIC-7902 (SE7501WV2S, i686, v7.2.11, not packetized) with
    the v2 code: device resets idle and under I/O, a device reset of the
    failing disk, and a bus reset. The new ahd_done() call is reached only
    by a reset answered with CHECK CONDITION, which these disks do not do.
    Build-tested with W=1 for x86_64 and i386, no new warnings.
    
    Prepared with LLM assistance (Claude Opus 5.5; v3 also reviewed by
    Grok); I reviewed it and ran the tests.

 drivers/scsi/aic7xxx/aic79xx_core.c |  4 +++-
 drivers/scsi/aic7xxx/aic79xx_osm.h  | 26 +++++++++++++++++++++-----
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c
index 3602a1fc4..4abc79481 100644
--- a/drivers/scsi/aic7xxx/aic79xx_core.c
+++ b/drivers/scsi/aic7xxx/aic79xx_core.c
@@ -8942,8 +8942,10 @@ ahd_handle_scsi_status(struct ahd_softc *ahd, struct scb *scb)
 		}
 #endif
 
-		if (ahd_perform_autosense(scb) == 0)
+		if (ahd_perform_autosense(scb) == 0) {
+			ahd_done(ahd, scb);
 			break;
+		}
 
 		ahd_compile_devinfo(&devinfo, SCB_GET_OUR_ID(scb),
 				    SCB_GET_TARGET(ahd, scb),
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h
index c6eb2b97e..1facfd238 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.h
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.h
@@ -501,6 +501,8 @@ int	ahd_linux_show_info(struct seq_file *,struct Scsi_Host *);
 static inline
 void ahd_cmd_set_transaction_status(struct scsi_cmnd *cmd, uint32_t status)
 {
+	if (!cmd)
+		return;
 	cmd->result &= ~(CAM_STATUS_MASK << 16);
 	cmd->result |= status << 16;
 }
@@ -514,6 +516,8 @@ void ahd_set_transaction_status(struct scb *scb, uint32_t status)
 static inline
 void ahd_cmd_set_scsi_status(struct scsi_cmnd *cmd, uint32_t status)
 {
+	if (!cmd)
+		return;
 	cmd->result &= ~0xFFFF;
 	cmd->result |= status;
 }
@@ -527,6 +531,8 @@ void ahd_set_scsi_status(struct scb *scb, uint32_t status)
 static inline
 uint32_t ahd_cmd_get_transaction_status(struct scsi_cmnd *cmd)
 {
+	if (!cmd)
+		return CAM_REQ_INPROG;
 	return ((cmd->result >> 16) & CAM_STATUS_MASK);
 }
 
@@ -539,6 +545,8 @@ uint32_t ahd_get_transaction_status(struct scb *scb)
 static inline
 uint32_t ahd_cmd_get_scsi_status(struct scsi_cmnd *cmd)
 {
+	if (!cmd)
+		return SAM_STAT_GOOD;
 	return (cmd->result & 0xFFFF);
 }
 
@@ -566,13 +574,16 @@ u_long ahd_get_transfer_length(struct scb *scb)
 static inline
 int ahd_get_transfer_dir(struct scb *scb)
 {
+	if (!scb->io_ctx)
+		return DMA_NONE;
 	return (scb->io_ctx->sc_data_direction);
 }
 
 static inline
 void ahd_set_residual(struct scb *scb, u_long resid)
 {
-	scsi_set_resid(scb->io_ctx, resid);
+	if (scb->io_ctx)
+		scsi_set_resid(scb->io_ctx, resid);
 }
 
 static inline
@@ -584,6 +595,8 @@ void ahd_set_sense_residual(struct scb *scb, u_long resid)
 static inline
 u_long ahd_get_residual(struct scb *scb)
 {
+	if (!scb->io_ctx)
+		return 0;
 	return scsi_get_resid(scb->io_ctx);
 }
 
@@ -597,11 +610,12 @@ static inline
 int ahd_perform_autosense(struct scb *scb)
 {
 	/*
-	 * We always perform autosense in Linux.
-	 * On other platforms this is set on a
-	 * per-transaction basis.
+	 * We always perform autosense in Linux, except for the device
+	 * reset SCB, which has no command to return sense data to.
 	 */
-	return (1);
+	if (!scb->io_ctx)
+		return 0;
+	return 1;
 }
 
 static inline uint32_t
@@ -631,6 +645,8 @@ void	ahd_platform_freeze_devq(struct ahd_softc *ahd, struct scb *scb);
 static inline void
 ahd_freeze_scb(struct scb *scb)
 {
+	if (!scb->io_ctx)
+		return;
 	if ((scb->io_ctx->result & (CAM_DEV_QFRZN << 16)) == 0) {
 		scb->io_ctx->result |= CAM_DEV_QFRZN << 16;
 		scb->platform_data->dev->qfrozen++;

base-commit: db8b4d2bf2d3e02b4ff78bbf69d00e11795840de
-- 
2.47.3